☆ Yσɠƚԋσʂ ☆@lemmygrad.ml to Technology@lemmygrad.mlEnglish · edit-211 days agoBaidu joins open-source movement by making Ernie 4.5 models publicly availablewww.scmp.comexternal-linkmessage-square2fedilinkarrow-up122arrow-down10file-text
arrow-up122arrow-down1external-linkBaidu joins open-source movement by making Ernie 4.5 models publicly availablewww.scmp.com☆ Yσɠƚԋσʂ ☆@lemmygrad.ml to Technology@lemmygrad.mlEnglish · edit-211 days agomessage-square2fedilinkfile-text
minus-squareKrasnaiaZvezda@lemmygrad.mllinkfedilinkarrow-up5·11 days agoNice of them to make even a 0.3B model, just too bad it was the only one that wasn’t MoE. I’ve been wanting more small MoEs since Qwen 30B A3B.
minus-square☆ Yσɠƚԋσʂ ☆@lemmygrad.mlOPlinkfedilinkarrow-up5·11 days agoOn a random note, I’d really love to see this approach explored more. It would be really handy to have models that can learn and evolve over time through usage https://github.com/babycommando/neuralgraffiti
Nice of them to make even a 0.3B model, just too bad it was the only one that wasn’t MoE. I’ve been wanting more small MoEs since Qwen 30B A3B.
On a random note, I’d really love to see this approach explored more. It would be really handy to have models that can learn and evolve over time through usage https://github.com/babycommando/neuralgraffiti